Metraipolis › archive › dc_dfbd606d2b8f
From Explanations to Interventions: Execution-Guided Counterfactual Synthesis in Temporal Graphs — arXiv:2609.11170
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.11170
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T05:23:44.863Z
- SHA-256 of the archived text
55a1e77c6f3d1b30310943a996f2088deed0a0ed2f305d093a77b72b1fd56a44- Stable URL of this page
https://metraipolis.com/documento/dc_dfbd606d2b8f
How to cite
From Explanations to Interventions: Execution-Guided Counterfactual Synthesis in Temporal Graphs — arXiv:2609.11170 — arXiv (en), https://arxiv.org/abs/2609.11170 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dfbd606d2b8f (Metraipolis archive dc_dfbd606d2b8f, sha256 55a1e77c6f3d1b30310943a996f2088deed0a0ed2f305d093a77b72b1fd56a44)
BibTeX
@misc{dcdfbd606d2b8f,
title = {From Explanations to Interventions: Execution-Guided Counterfactual Synthesis in Temporal Graphs — arXiv:2609.11170},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.11170},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dfbd606d2b8f; sha256 55a1e77c6f3d1b30310943a996f2088deed0a0ed2f305d093a77b72b1fd56a44},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11170. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Can a trace explaining model execution also compute the changes needed for a specified alternative prediction? We propose trace-guided intervention search, which uses executable reasoning traces as an intermediate representation for intervention synthesis. A Specified-Foil Counterfactual edits past events so that a frozen temporal predictor selects a designated foil. Our method constructs facts and replacement values from completed original and foil executions and recovered unmet conditions. Proposal generation constructs edits and selects candidates within a fixed cap; exact replay verifies foil top-1 outcomes among retained edits and compositions. Implemented in LiFTER for continuous-time dynamic graphs (CTDGs) and TLogic for temporal knowledge graphs (TKGs), the method improves success over coordinate-based proposal generation by 13.7-34.7 percentage points on four CTDG datasets and 60.0-83.3 points on two TKG datasets under matched downstream search and a proposal cap of 32. Separate shared-candidate comparisons retain 85.7-93.6% of black-box greedy's CTDG success rate with 75.0-80.0% fewer predictor evaluations. A Pulse case study confirms simulator-level survival for five of six interventions. Executable traces thus provide both explanatory evidence and a reusable computational representation for constructing and testing specified alternatives. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.11170 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T05:17:51.977Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).